基于信息素的最优推理路径学习
Pheromone-based Learning of Optimal Reasoning Paths
AI总结：
本文提出ACO-ToT算法，结合蚁群优化与LLM，利用微调的“蚂蚁”模型在思维树中留下信息素轨迹，并通过混合专家评分强化有效路径，显著提升了复杂推理任务的性能。
摘要：
大型语言模型（LLMs）通过思维链提示展现了卓越的推理能力，然而由于可能的中间步骤空间巨大，为复杂问题发现有效的推理方法仍然具有挑战性。我们引入了蚁群优化引导的思维树（ACO-ToT），这是一种将ACO与LLMs相结合的新颖算法，旨在高效地发现复杂问题的最优推理路径。受神经系统赫布学习的启发，我们的方法采用一组经过特定微调的LLM“蚂蚁”，在集中式思维树中遍历并留下信息素轨迹，每只蚂蚁的移动由现有信息素轨迹与其自身专业知识的加权组合所控制。该算法使用基于混合专家的评分函数评估完整的推理路径，并通过信息素在迭代中强化有效的推理路径。在三个具有挑战性的推理任务（GSM8K、ARC-Challenge和MATH）上的实验表明，ACO-ToT的表现显著优于现有的思维链优化方法，这表明将受生物学启发的集体搜索机制纳入LLM推理可以大幅提升推理能力。
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities through chain-of-thought prompting, yet discovering effective reasoning methods for complex problems remains challenging due to the vast space of possible intermediate steps. We introduce Ant Colony Optimization-guided Tree of Thought (ACO-ToT), a novel algorithm that combines ACO with LLMs to discover optimal reasoning paths for complex problems efficiently. Drawing inspiration from Hebbian learning in neurological systems, our method employs a collection of distinctly fine-tuned LLM "ants" to traverse and lay pheromone trails through a centralized tree of thought, with each ant's movement governed by a weighted combination of existing pheromone trails and its own specialized expertise. The algorithm evaluates complete reasoning paths using a mixture-of-experts-based scoring function, with pheromones reinforcing productive reasoning paths across iterations. Experiments on three challenging reasoning tasks (GSM8K, ARC-Challenge, and MATH) demonstrate that ACO-ToT performs significantly better than existing chain-of-thought optimization approaches, suggesting that incorporating biologically inspired collective search mechanisms into LLM inference can substantially enhance reasoning capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
